SJ

SJT Moe2x7.5B IQ4 XS

SjtGGUF by roleplaiappUpdated 2025-02-03
Download on Hugging Face
Parameters13.4B
Context32K
Layers28
Architecturellama
Smallest quant7.3 GB
Quick answer

SJT Moe2x7.5B IQ4 XS needs about 8.7 GB of memory at IQ4_XS (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

SJT Moe2x7.5B IQ4 XS is a 13.4B-parameter Sjt model in GGUF format, quantized by roleplaiapp. Its trained context length is 32K tokens. The repository has 1 quant file, from 7.3 GB (IQ4_XS) to 7.3 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS7.3 GB 8.7 GB
Too big Get file →

What GPU do you need for SJT Moe2x7.5B IQ4 XS?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ4_XS (7.3 GB file, about 8.7 GB in use).

Which SJT Moe2x7.5B IQ4 XS quant should you choose?

IQ4_XS (7.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.4B (approximate, mixture of experts)
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized byroleplaiapp
FamilySjt
Licenseapache-2.0
Downloads (HF)5
Last updated2025-02-03

Frequently asked questions about SJT Moe2x7.5B IQ4 XS

How much VRAM does SJT Moe2x7.5B IQ4 XS need?

About 8.7 GB at IQ4_XS with an 8K context window. That is the 7.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run SJT Moe2x7.5B IQ4 XS on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SJT Moe2x7.5B IQ4 XS GGUF?

It depends on the quant: IQ4_XS is 7.3 GB.

What context length does SJT Moe2x7.5B IQ4 XS support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download SJT Moe2x7.5B IQ4 XS GGUF?

The files are on Hugging Face in the roleplaiapp/SJT-Moe2x7.5B-IQ4_XS-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SJT Moe2x7.5B IQ4 XS use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from roleplaiapp

All by roleplaiapp →

More Sjt models

All Sjt →

Other medium models

All medium models →